Skip to content

Significant performance boost: only write to the writer schema cache once. #724

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 4 commits into from
Closed

Significant performance boost: only write to the writer schema cache once. #724

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
98fd822
Only write to the writer schema cache once.
fimmtiu Nov 25, 2019
6150f32
Add test for the _get_encoder_func caching.
fimmtiu Dec 12, 2019
e611711
Patch against self.ms, change iterators to list for reuse across test…
bstaudacher Dec 12, 2019
95f2620
Merge pull request #1 from fimmtiu/add-test-for-schema-cache
fimmtiu Dec 17, 2019
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 2 additions & 1 deletion confluent_kafka/avro/serializer/message_serializer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -110,7 +110,8 @@ def encode_record_with_schema(self, topic, schema, record, is_key=False):
raise serialize_err(message)

# cache writer
self.id_to_writers[schema_id] = self._get_encoder_func(schema)
if schema_id not in self.id_to_writers:
self.id_to_writers[schema_id] = self._get_encoder_func(schema)

return self.encode_record_with_schema_id(schema_id, record, is_key=is_key)

Expand Down
4 changes: 2 additions & 2 deletions tests/avro/data_gen.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -54,7 +54,7 @@ def create_basic_item(i):
}


BASIC_ITEMS = map(create_basic_item, range(1, 20))
BASIC_ITEMS = list(map(create_basic_item, range(1, 20)))

ADVANCED_SCHEMA = load_schema_file(os.path.join(avsc_dir, 'adv_schema.avsc'))

Expand All @@ -68,7 +68,7 @@ def create_adv_item(i):
return basic


ADVANCED_ITEMS = map(create_adv_item, range(1, 20))
ADVANCED_ITEMS = list(map(create_adv_item, range(1, 20)))


def _write_items(base_name, schema_str, items):
Expand Down
14 changes: 13 additions & 1 deletion tests/avro/test_message_serializer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,6 +23,7 @@
import struct

import unittest
from unittest.mock import patch

from tests.avro import data_gen
from confluent_kafka.avro.serializer.message_serializer import MessageSerializer
Expand Down Expand Up @@ -75,8 +76,19 @@ def test_encode_record_with_schema(self):
message = self.ms.encode_record_with_schema(topic, basic, record)
self.assertMessageIsSame(message, record, schema_id)

def test_encode_record_with_schema_sets_writers_cache_once(self):
topic = 'test'
basic = avro.loads(data_gen.BASIC_SCHEMA)
subject = 'test-value'
self.client.register(subject, basic)
records = data_gen.BASIC_ITEMS
with patch.object(self.ms, "_get_encoder_func") as encoder_func_mock:
for record in records:
self.ms.encode_record_with_schema(topic, basic, record)
encoder_func_mock.assert_called_once_with(basic)

def test_decode_none(self):
""""null/None messages should decode to None"""
"""null/None messages should decode to None"""

self.assertIsNone(self.ms.decode_message(None))

Expand Down